[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

Essentially the same as the GEP change in r230786.

A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)

import fileinput
import sys
import re

pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")

for line in sys.stdin:
  sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))

Reviewers: rafael, dexonsmith, grosser

Differential Revision: http://reviews.llvm.org/D7649

llvm-svn: 230794
diff --git a/llvm/test/CodeGen/R600/lds-output-queue.ll b/llvm/test/CodeGen/R600/lds-output-queue.ll
index f34cad4..44ffc36 100644
--- a/llvm/test/CodeGen/R600/lds-output-queue.ll
+++ b/llvm/test/CodeGen/R600/lds-output-queue.ll
@@ -13,11 +13,11 @@
 define void @lds_input_queue(i32 addrspace(1)* %out, i32 addrspace(1)* %in, i32 %index) {
 entry:
   %0 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* @local_mem, i32 0, i32 %index
-  %1 = load i32 addrspace(3)* %0
+  %1 = load i32, i32 addrspace(3)* %0
   call void @llvm.AMDGPU.barrier.local()
 
   ; This will start a new clause for the vertex fetch
-  %2 = load i32 addrspace(1)* %in
+  %2 = load i32, i32 addrspace(1)* %in
   %3 = add i32 %1, %2
   store i32 %3, i32 addrspace(1)* %out
   ret void
@@ -41,8 +41,8 @@
 ; has been declared in the local memory space:
 ;
 ;  %0 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* @local_mem, i32 0, i32 %index
-;  %1 = load i32 addrspace(3)* %0
-;  %2 = load i32 addrspace(1)* %in
+;  %1 = load i32, i32 addrspace(3)* %0
+;  %2 = load i32, i32 addrspace(1)* %in
 ;
 ; The instruction selection phase will generate ISA that looks like this:
 ; %OQAP = LDS_READ_RET
@@ -91,8 +91,8 @@
 define void @local_global_alias(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
 entry:
   %0 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(3)* @local_mem, i32 0, i32 0
-  %1 = load i32 addrspace(3)* %0
-  %2 = load i32 addrspace(1)* %in
+  %1 = load i32, i32 addrspace(3)* %0
+  %2 = load i32, i32 addrspace(1)* %in
   %3 = add i32 %2, %1
   store i32 %3, i32 addrspace(1)* %out
   ret void